What is pr-walkthrough?

A Markdown walkthrough of a pull request, a proposed set of changes to a code repository, based on the pull request's files, diffs, metadata, and commit summaries.

It is for producing a reviewer-oriented, slide-ready explanation of a pull request, with plain Markdown as a fallback.

Reviewers can spend time reconstructing what changed and where. This creates an evidence-based guide to the changes without judging whether the pull request is correct.

pr-walkthrough — Skill for Claude Code by rp1-run

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add rp1-run/rp1 --skill pr-walkthrough

Clone the repo

git clone --depth 1 https://github.com/rp1-run/rp1

Made for: Claude Code.

Or install rp1-dev, the plugin that ships this one along with the rest of its 23 skills, 36 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/rp1-run/rp1/pr-walkthrough/github.svg)](https://agentmods.dev/skills/rp1-run/rp1/pr-walkthrough)

Your own site

<a href="https://agentmods.dev/skills/rp1-run/rp1/pr-walkthrough"><img src="https://agentmods.dev/badge/skills/rp1-run/rp1/pr-walkthrough/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/rp1-run/rp1/pr-walkthrough"><img src="https://agentmods.dev/badge/skills/rp1-run/rp1/pr-walkthrough.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,236 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00017	$0.02236
Opus 5	$0.00009	$0.01118
Sonnet 5	$0.00003	$0.00447
Haiku 4.5	$0.00002	$0.00224

Measured 2d ago against content hash 0739be2d5955, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

pr-walkthrough scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/dev/skills/pr-walkthrough/SKILL.md · 237 lines

How it starts

The opening of the file, as written. The whole thing — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PR Walkthrough

Generate a slide-ready markdown walkthrough from direct pull request evidence. The output is a reviewer-orientation artifact with plain markdown fallback, not a review verdict or rendered slide reader.

Use the pre-resolved projectRoot, kbRoot, workRoot, and codeRoot values from the generated Workflow Bootstrap section. Run all source-control commands from codeRoot, and write generated artifacts only under workRoot.

Do not read .rp1/work/pr-reviews/ or any existing pr-review artifacts as source material. The walkthrough source of truth is the target PR metadata, changed files, diffs, and commit summaries gathered in this workflow.

STATE-MACHINE

stateDiagram-v2
    [*] --> collecting
    collecting --> publishing : evidence_ready
    publishing --> [*] : done

On each phase transition, report via:

rp1 agent-tools emit \
  --workflow pr-walkthrough \
  --type status_change \
  --run-id {RUN_ID} \
  --step {CURRENT_STATE} \
  --data '{"status": "running"}'

RUN_ID comes from the generated Workflow Bootstrap section.
Derive RUN_NAME from the resolved target: use "PR Walkthrough: PR #{number}" when a PR number is available, otherwise "PR Walkthrough: {branch_name}".
On the first emit only, include --name "{RUN_NAME}".

Example sequence:

rp1 agent-tools emit --workflow pr-walkthrough --type status_change --run-id {RUN_ID} --name "PR Walkthrough: PR #42" --step collecting --data '{"status": "running"}'
rp1 agent-tools emit --workflow pr-walkthrough --type status_change --run-id {RUN_ID} --step publishing --data '{"status": "running"}'
rp1 agent-tools emit --workflow pr-walkthrough --type status_change --run-id {RUN_ID} --step publishing --data '{"status": "completed"}'

On a blocking error, emit the current step with {"status":"failed","reason":"..."} and stop without dispatching the reporter or registering an artifact.

1. Collect Direct Evidence

Execute immediately. Do not ask for clarification. Fail clearly during collecting when the target cannot identify one PR or one local diff.

Read the full file on GitHub · 237 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2d ago First seen · 237 lines · 17 tokens per session scan A 0739be2d5955

Subscribe to this mod's changes

pr-walkthrough is a skill published in the GitHub repository rp1-run/rp1 (38 stars, last pushed 2d ago), licensed Apache-2.0. It adds 17 tokens to every session and 2,236 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-07.

Code review Git and workflow ai context-engineering developer-tools opencode prompt-engineering

pr-splitter

Analyse an oversized pull request or proposed branch changeset and decompose it into smaller, dependency-aware, independently reviewable pull requests. Use when a PR is too large for effective review or when the user asks to split, stack, or repackage a feature branch without changing its final behaviour. Do not use…

kabudu/engineering-agent-skills · 75 tokens

smart-pr-generator

Analyzes Git diffs (staged or unstaged) and generates conventional commit messages and detailed, slop-free Pull Request descriptions.

aragaobruno/toolbelt · 31 tokens

comprehensive-review-pr-enhance

You are a PR optimization expert specializing in creating high-quality pull requests that facilitate efficient code reviews. Generate comprehensive PR descriptions, automate review processes, and ensure PRs follow best practices for clarity, size, and reviewability.

Dokhacgiakhoa/Agent-Skills-4-Vibe-Coding-CLI · 51 tokens

pr-walkthrough